CN106595496A - Man-machine interaction part size flexibility vision measurement method - Google Patents
Man-machine interaction part size flexibility vision measurement method Download PDFInfo
- Publication number
- CN106595496A CN106595496A CN201710122527.5A CN201710122527A CN106595496A CN 106595496 A CN106595496 A CN 106595496A CN 201710122527 A CN201710122527 A CN 201710122527A CN 106595496 A CN106595496 A CN 106595496A
- Authority
- CN
- China
- Prior art keywords
- image
- measured
- interest
- feature
- diameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/08—Measuring arrangements characterised by the use of optical techniques for measuring diameters
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The present invention discloses a man-machine interaction part size flexibility vision measurement method. The method comprises: calibrating the installation position of an industrial camera; disposing a circular landmark with a known accurate size on the measurement position, collecting the image of the circular landmark, employing an image circle feature extraction method to obtain the size of the diameter of the landmark taking the pixel as a unit in the image, and calculating the objective image proportion coefficient of the test image; arranging a tested part on the measurement position, collecting the tested part image and displaying the tested part image; selecting an image region where the features to be tested on the tested part image; setting the image region where the features to be tested as a region of interest; and if the characteristics of the features to be tested are the diameters of the circle and the hole, and selecting the diameter measurement algorithm to perform image processing of the ROI (region of interest) to obtain and output the diameter size or the length size. The man-machine interaction part size flexibility vision measurement method enlarges the application range of the vision measurement technology, and is simple in operation, easy to ensure the measurement precision, good in stability and low in the requirement of the usage environment.
Description
Technical field
The present invention relates to Computer Vision Detection Technique field, particularly a kind of man-machine interaction accessory size flexibility vision survey
Amount method.
Background technology
Computer vision technique has the advantages that untouchable, economy, motility and integration, industrial test with
Line detection field is with a wide range of applications.During the processing and manufacturing of part, it is not that the size of part is measured
One of committed step that can or lack.Traditional manual measurement method has that workload is big, efficiency is low, precision is difficult to ensure that etc. and asks
Topic.In recent years, with the fast development of computer vision technique, some accessory size vision measurement systems are occurred in that, these are
System is capable of achieving the automatic measurement of a certain or a certain class accessory size, substantially increases working ability, production efficiency and product
Quality.But, being limited by vision measurement state-of-art at this stage, the image processing algorithm of these systems is for spy
The construction featuress of fixed a certain or a certain class part and measurement requirement design, after tested part is replaced with, these systems are past
Toward the measurement requirement that all can not adapt to automatically new parts, need to develop again image processing algorithm, this problem limits vision
Popularization of the e measurement technology in part processing and manufacturing industry.
The content of the invention
The technical problem to be solved is, not enough for prior art, there is provided a kind of man-machine interaction accessory size
Flexible vision measuring method.
To solve above-mentioned technical problem, the technical solution adopted in the present invention is:A kind of man-machine interaction accessory size is flexible
Vision measuring method, comprises the following steps:
1) installation site of industrial camera is calibrated, industrial camera and tested part placement platform keeping parallelism is made;
2) circle marker thing known to a size is placed on the measuring location, and circle marker thing is gathered by industrial camera
Image, and adopt image circle feature extracting method to obtain the circle marker thing diameter in the picture in units of pixel, calculate
The image proportionality coefficient of image;
3) tested part is placed in measurement position, tested part image is gathered by industrial camera, and in industry meter
Tested part image is shown on calculation machine;
4) image-region at feature place to be measured is selected on tested part image, and the property of the feature to be measured is set;
5) image-region that feature to be measured is located is set to into area-of-interest;
If 6) set characteristic properties to be measured as circle, the diameter in hole, choosing diameter measurement algorithm is carried out to area-of-interest
Image procossing, and the image proportionality coefficient is utilized, obtain diameter and export;If setting characteristic properties to be measured as the length of straight line
Degree, then choose linear measure longimetry algorithm carries out image procossing to area-of-interest, and utilizes the image proportionality coefficient, obtains length
And export;
7) repeat step 4)~6) until the feature all to be measured of tested part completes dimensional measurement.Step 4) in, treat
The determination method for surveying the image-region that feature is located is comprised the following steps:
1) on tested part image feature to be measured upper left corner selected point A, obtain image coordinate and fasten the coordinate of point A
(xa,ya);
2) on tested part image feature to be measured lower right corner selected point C, obtain image coordinate and fasten the coordinate of point C
(xc,yc);
3) image-region that feature to be measured is located is set as with line segment AC as cornerwise rectangular area.Step 6) in, directly
The calculating process in footpath is comprised the following steps:
1) using making an uproar that morphology opening and closing bilateral filtering method elimination area-of-interest A is produced in collection and transmission
Sound and visual beacon thing disappearance, obtain enhanced area-of-interest A';
2) edge graph of A' is obtained using Canny edge detection methods;
3) circle in A' edge graphs, bore dia L are asked for using Hough circle transformation;
4) actual diameter N is calculated than row coefficient k by diameter L images, computing formula is:N=L × k.
The calculating process of length includes:
1) using making an uproar that morphology opening and closing bilateral filtering method elimination area-of-interest A is produced in collection and transmission
Sound and visual beacon thing disappearance, obtain enhanced area-of-interest A';
2) edge graph of A' is obtained using Canny edge detection methods;
3) the straight length L ' in image A' is asked for using the conversion of Hough lines;
4) by length L ' and image than row coefficient k, be calculated physical length N ', computing formula is:N'=L' × k.
The computing formula of image proportionality coefficient k is:Wherein, actual diameters of the s for circle marker thing, unit are milli
Rice;P is to adopt image circle feature extracting method to obtain diameter corresponding picture of the circle marker thing in the picture in units of pixel
Plain number.
Compared with prior art, the present invention it is had the advantage that for:The present invention is capable of achieving to not by man-machine interaction
With the size vision measurement of species part so that vision measurement technology can be used in single-piece, parts in small batch processing occasion, expanded
The scope of application of vision measurement technology;Easy to operate, certainty of measurement is easily guaranteed that;The image characteristics extraction side that the present invention is adopted
Method is the good stability based on the very strong Hough transform of robustness, use environment is required low;The present invention can be with
Further expand, so as to adapt to the measurement of more features to be measured (such as length of curve, curvature etc.).
Description of the drawings
Fig. 1 is one embodiment of the invention method flow diagram;
Fig. 2 is the round feature extracting method flow chart in step 2 of the present invention;
Fig. 3 is to determine that geometric properties place image-region method is illustrated according to operator's mouse action in step 4 of the present invention
Figure, in figure:1-feature to be measured, 2-image-region;
Fig. 4 is diameter measurement algorithm flow chart in step 6 of the present invention;
Fig. 5 is linear measure longimetry algorithm flow chart in step 6 of the present invention.
Specific embodiment
As shown in figure 1, a target of the invention is that round embodiment dividing method process is as follows:
It is before starting measurement, first that industrial camera is rack-mount, the installation site of industrial camera is calibrated, industrial camera is made
With tested part placement platform keeping parallelism;Then the accurately known circle marker thing of a size is placed on the measuring location, is surveyed
Amount software gathers circle marker object image by industrial camera, and obtains the mark in figure using image circle feature extracting method
Diameter dimension as in units of pixel, calculates the image proportionality coefficient of test image, the image circle feature extraction side of employing
Method is referring to accompanying drawing 2.
Then, start to measure tested part, first tested part is placed in measurement position, Survey Software passes through
Industrial camera gathers tested part image, and tested part image is shown on industrial computer;System operators pass through Mus
The image-region that feature to be measured is located is selected in mark operation on tested part image, and arranges the property of the feature to be measured.Wherein,
Geometric properties region determines method referring to accompanying drawing 3:Mouse is moved to be measured on tested part image by system operators
The upper left corner of feature, single left button mouse click, Survey Software obtain the coordinate A (x that current mouse is fastened in image coordinatea,ya);System
Mouse is moved to system operator the lower right corner of feature to be measured on tested part image, again a mouse click right button, is measured soft
Part obtains the coordinate C (x that current mouse is fastened in image coordinatec,yc);Then image-region is set as with line segment AC as cornerwise
Rectangular area.The image-region that feature to be measured is located is set to area-of-interest (ROI) by Survey Software.
If system operators set characteristic properties to be measured as the diameter in (circle, hole), Survey Software chooses diameter measurement
Algorithm carries out image procossing to ROI, obtains diameter dimension and exports;If system operators set characteristic properties to be measured as (straight
Line) length, then Survey Software choose linear measure longimetry algorithm image procossing is carried out to ROI, obtain length dimension and export.Using
Diameter measurement algorithm referring to accompanying drawing 4, the linear measure longimetry algorithm of employing is referring to accompanying drawing 5.
Then system operators are selected next feature region to be measured on tested part image and arrange feature
Property, Survey Software are special again by area-of-interest, diameter measurement algorithm (or linear measure longimetry algorithm) the measurement next one is arranged
The size levied, and result is exported.On tested part, all features to be measured all complete measurement, then the size of the part is surveyed
Amount is finished.
The present invention is capable of achieving the size vision measurement to variety classes part so that vision measurement skill by man-machine interaction
Art can be used in single-piece, parts in small batch processing occasion, expand the scope of application of vision measurement technology;Easy to operate, measurement
Precision is easily guaranteed that;The image characteristic extracting method that adopts of the present invention be based on the very strong Hough transform of robustness,
Good stability, requires to use environment low;The present invention further can also expand, so as to adapt to more features to be measured (such as curve
Length, curvature etc.) measurement.
Claims (5)
1. a kind of man-machine interaction accessory size flexibility vision measuring method, it is characterised in that comprise the following steps:
1) installation site of industrial camera is calibrated, industrial camera and tested part placement platform keeping parallelism is made;
2) circle marker thing known to a size is placed on the measuring location, and the figure of circle marker thing is gathered by industrial camera
Picture, and adopt image circle feature extracting method to obtain the circle marker thing diameter in the picture in units of pixel, calculate figure
The image proportionality coefficient of picture;
3) tested part is placed in measurement position, tested part image is gathered by industrial camera, and in industrial computer
Upper display tested part image;
4) image-region at feature place to be measured is selected on tested part image, and the property of the feature to be measured is set;
5) image-region that feature to be measured is located is set to into area-of-interest;
If 6) set characteristic properties to be measured as circle, the diameter in hole, choosing diameter measurement algorithm carries out image to area-of-interest
Process, and utilize the image proportionality coefficient, obtain area-of-interest actual diameter and export;If set characteristic properties to be measured as
The length of straight line, then choose linear measure longimetry algorithm carries out image procossing to area-of-interest, and utilizes the image proportionality coefficient,
Obtain area-of-interest physical length and export;
7) repeat step 4)~6) until the feature all to be measured of tested part completes dimensional measurement.
2. man-machine interaction accessory size according to claim 1 flexibility vision measuring method, it is characterised in that
Step 4) in, the determination method of the image-region that feature to be measured is located is comprised the following steps:
1) on tested part image feature to be measured upper left corner selected point A, obtain image coordinate and fasten the coordinate (x of point Aa,
ya);
2) on tested part image feature to be measured lower right corner selected point C, obtain image coordinate and fasten the coordinate (x of point Cc,
yc);
3) image-region that feature to be measured is located is set as with line segment AC as cornerwise rectangular area.
3. man-machine interaction accessory size according to claim 1 flexibility vision measuring method, it is characterised in that step 6)
In, the calculating process of diameter is comprised the following steps:
1) using morphology be opened and closed bilateral filtering method eliminate noise that area-of-interest A produced in collection and transmission and
Visual beacon thing is lacked, and obtains enhanced area-of-interest A';
2) edge graph of A' is obtained using Canny edge detection methods;
3) circle in A' edge graphs, bore dia L are asked for using Hough circle transformation;
4) by diameter L and image proportionality coefficient k, actual diameter N is calculated, computing formula is:N=L × k.
4. man-machine interaction accessory size according to claim 1 flexibility vision measuring method, it is characterised in that
The calculating process of length includes:
1) using morphology be opened and closed bilateral filtering method eliminate noise that area-of-interest A produced in collection and transmission and
Visual beacon thing is lacked, and obtains enhanced area-of-interest A';
2) edge graph of A' is obtained using Canny edge detection methods;
3) the straight length L ' in image A' is asked for using the conversion of Hough lines;
4) by length L ' and image proportionality coefficient k, it is calculated physical length N ', computing formula is:N'=L' × k.
5. the flexible vision measuring method of man-machine interaction accessory size according to one of Claims 1 to 4, it is characterised in that
The computing formula of image proportionality coefficient k is:Wherein, actual diameters of the s for circle marker thing, unit is millimeter;P is to adopt
Diameter corresponding number of pixels of the circle marker thing in the picture in units of pixel is obtained with image circle feature extracting method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710122527.5A CN106595496A (en) | 2017-03-03 | 2017-03-03 | Man-machine interaction part size flexibility vision measurement method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710122527.5A CN106595496A (en) | 2017-03-03 | 2017-03-03 | Man-machine interaction part size flexibility vision measurement method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106595496A true CN106595496A (en) | 2017-04-26 |
Family
ID=58588199
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710122527.5A Pending CN106595496A (en) | 2017-03-03 | 2017-03-03 | Man-machine interaction part size flexibility vision measurement method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106595496A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108230386A (en) * | 2018-01-05 | 2018-06-29 | 湖北汽车工业学院 | A kind of image processing algorithm in automobile tube beam measurement |
CN108253895A (en) * | 2018-02-23 | 2018-07-06 | 广州飞机维修工程有限公司 | A kind of material surface crackle straight length measuring method based on image procossing |
CN109035230A (en) * | 2018-07-19 | 2018-12-18 | 中导光电设备股份有限公司 | A kind of Circularhole diameter vision measuring method |
CN109509182A (en) * | 2018-10-29 | 2019-03-22 | 首都航天机械有限公司 | A kind of typical products geometric dimension measurement method and system based on image procossing |
CN109579715A (en) * | 2017-09-28 | 2019-04-05 | 宝山钢铁股份有限公司 | A kind of digitlization On-line Measuring Method improving hole expansibility measurement accuracy |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103063159A (en) * | 2012-12-31 | 2013-04-24 | 南京信息工程大学 | Part size measurement method based on charge coupled device (CCD) |
-
2017
- 2017-03-03 CN CN201710122527.5A patent/CN106595496A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103063159A (en) * | 2012-12-31 | 2013-04-24 | 南京信息工程大学 | Part size measurement method based on charge coupled device (CCD) |
Non-Patent Citations (2)
Title |
---|
刘霞: "工业零件形状尺寸的机器视觉检测系统的研究", 《中国优秀硕士学位论文全文数据库》 * |
许光明等: "基于视觉的零件尺寸测量", 《工业控制计算机》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109579715A (en) * | 2017-09-28 | 2019-04-05 | 宝山钢铁股份有限公司 | A kind of digitlization On-line Measuring Method improving hole expansibility measurement accuracy |
CN108230386A (en) * | 2018-01-05 | 2018-06-29 | 湖北汽车工业学院 | A kind of image processing algorithm in automobile tube beam measurement |
CN108253895A (en) * | 2018-02-23 | 2018-07-06 | 广州飞机维修工程有限公司 | A kind of material surface crackle straight length measuring method based on image procossing |
CN109035230A (en) * | 2018-07-19 | 2018-12-18 | 中导光电设备股份有限公司 | A kind of Circularhole diameter vision measuring method |
CN109035230B (en) * | 2018-07-19 | 2021-11-09 | 中导光电设备股份有限公司 | Round hole diameter visual measurement method |
CN109509182A (en) * | 2018-10-29 | 2019-03-22 | 首都航天机械有限公司 | A kind of typical products geometric dimension measurement method and system based on image procossing |
CN109509182B (en) * | 2018-10-29 | 2021-03-26 | 首都航天机械有限公司 | Typical product geometric dimension measuring method and system based on image processing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106595496A (en) | Man-machine interaction part size flexibility vision measurement method | |
CN105091922B (en) | A kind of pointer gauge Recognition of Reading method based on virtual dial plate | |
CN109883533B (en) | Low-frequency vibration measurement method based on machine vision | |
CN110659636B (en) | Pointer instrument reading identification method based on deep learning | |
CN106097361B (en) | Defect area detection method and device | |
Gong et al. | A handheld device for leaf area measurement | |
CN102176228B (en) | Machine vision method for identifying dial plate information of multi-pointer instrument | |
CN108257121B (en) | Method, apparatus, storage medium and the terminal device that product defects detection model updates | |
CN105300482B (en) | Water meter calibration method, apparatus based on image procossing and system | |
CN108182433A (en) | A kind of meter reading recognition methods and system | |
CN104657711B (en) | A kind of readings of pointer type meters automatic identifying method of robust | |
CN104392206A (en) | Image processing method for automatic pointer-type instrument reading recognition | |
CN111368906B (en) | Pointer type oil level meter reading identification method based on deep learning | |
WO2010030056A1 (en) | Automatic contour detection method for ultrasonic diagnosis appartus | |
CN103308430A (en) | Method and device for measuring weight of thousand of seeds | |
CN105547602A (en) | Subway tunnel segment leakage water remote measurement method | |
CN110223355B (en) | Feature mark point matching method based on dual epipolar constraint | |
CN103149087B (en) | Follow-up window and digital image-based non-contact real-time strain measurement method | |
CN103925878A (en) | Hole set detection method and system based on Hough round convolution transformation algorithm | |
CN103954334A (en) | Fully automatic image pickup type water meter verification system and operating method thereof | |
CN104680526A (en) | Method for measuring uniform particle size based on auto-correlation algorithm | |
CN109727226A (en) | A kind of position table automatic generation method based on machine learning | |
CN107561736B (en) | LCD defect detection method based on Fourier transform and Hough transform | |
CN105423975A (en) | Calibration system and method of large-size workpiece | |
CN103674177B (en) | A kind of signal processing method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170426 |